© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37160
    Prev
    Next
    INDEX
    Explanations

    comment section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ored
    -0.09
    apas
    -0.09
    uis
    -0.09
    åŁºæľ¬æĥħåĨµ
    -0.09
    ÑĤин
    -0.08
    åĬŁ
    -0.08
    .getIndex
    -0.08
    鼷
    -0.08
    ase
    -0.08
    rica
    -0.08
    POSITIVE LOGITS
     коллекÑĤив
    0.11
    çŁ³åĮĸ
    0.10
    åıįé¦Ī
    0.10
    对该
    0.09
    äºĴåĬ¨
    0.09
    çIJĨæĢ§
    0.09
    个
    0.09
    æĹłäºº
    0.08
    è¯Ŀé¢ĺ
    0.08
    éĿĴæµ·çľģ
    0.08
    Activations Density 0.020%

    No Known Activations